Counterfactual Explanations for Power System Optimisation

TL;DR

This paper introduces a framework using counterfactual explanations to interpret power system optimisation decisions, enhancing transparency in electricity markets by identifying minimal input changes that alter dispatch outcomes.

Contribution

It develops a novel bilevel optimisation approach for counterfactual explanations in power system problems, combining data-driven heuristics with traditional methods for improved efficiency and tractability.

Findings

Data-driven heuristics significantly speed up explanations.

Counterfactuals reveal key factors influencing dispatch decisions.

The approach improves transparency in complex power system optimisation.

Abstract

Enhanced computational capabilities of modern decision-making software have allowed us to solve increasingly sophisticated optimisation problems. But in complex socio-economic, technical environments such as electricity markets, transparent operation is key to ensure a fair treatment of all parties involved, particularly regarding dispatch decisions. We address this issue by building on the concept of counterfactual explanations, answering questions such as "Why was this generator not dispatched?" by identifying minimum changes in the input parameters that would have changed the optimal solution. Both DC Optimal Power Flow and Unit Commitment problems are considered, wherein the variable parameters are the spatial and temporal demand profiles, respectively. The thereby obtained explanations allow users to identify the most important differences between the real and expected market outcomes and observe which constraints have led to the solution. The framework uses a bilevel optimisation problem to find the counterfactual demand scenarios. State-of-the-art methods are compared with data-driven heuristics on the basis of computational efficiency and explanation accuracy. Results show that leveraging historical data from previously solved instances can provide significant speed benefits and allows us to derive explanations in cases where conventional methods would not be tractable.